Journal ArticleDOI
Learnability and the Vapnik-Chervonenkis dimension
Reads0
Chats0
TLDR
This paper shows that the essential condition for distribution-free learnability is finiteness of the Vapnik-Chervonenkis dimension, a simple combinatorial parameter of the class of concepts to be learned.Abstract:
Valiant's learnability model is extended to learning classes of concepts defined by regions in Euclidean space En. The methods in this paper lead to a unified treatment of some of Valiant's results, along with previous results on distribution-free convergence of certain pattern recognition algorithms. It is shown that the essential condition for distribution-free learnability is finiteness of the Vapnik-Chervonenkis dimension, a simple combinatorial parameter of the class of concepts to be learned. Using this parameter, the complexity and closure properties of learnable classes are analyzed, and the necessary and sufficient conditions are provided for feasible learnability.read more
Citations
More filters
Book ChapterDOI
A space-bounded learning algorithm for axis-parallel rectangles
TL;DR: This work presents an on-line learning algorithm for BOX n d with the same learning complexity, time complexity O(d3log n) which is 2d-space-bounded and improves the best known algorithm due to Chen and Maass.
Book ChapterDOI
Two Algorithms for Solving the Walrasian Equilibrium Inequalities
Donald J. Brown,Ravi Kannan +1 more
TL;DR: In this paper, the authors propose two algorithms for deciding if the Walrasian equilibrium inequalities are solvable, which can serve as nonparametric tests for multiple calibration of applied general equilibrium models or they can be used to compute counterfactual equilibria.
Posted Content
Bennett-type Generalization Bounds: Large-deviation Case and Faster Rate of Convergence
TL;DR: In this paper, the authors present the Bennett-type generalization bounds of the learning process for i.i.d. samples, and then show that these bounds have a faster rate of convergence than the traditional results.
Posted Content
Statistical Active Learning Algorithms for Noise Tolerance and Differential Privacy
TL;DR: This work describes a framework for designing efficient active learning algorithms that are tolerant to random classification noise and are differentially-private and shows that commonly studied concept classes including thresholds, rectangles, and linear separators can be efficiently actively learned in this framework.
Learning multivalued multithreshold functions
TL;DR: A simple description of an algorithm based on a procedure suggested by Takiyama is given, and some open questions on the effectiveness of this algorithm are raised, and on the complexity of finding consistent hypotheses for samples of multithreshold functions are raised.
References
More filters
Book
Computers and Intractability: A Guide to the Theory of NP-Completeness
TL;DR: The second edition of a quarterly column as discussed by the authors provides a continuing update to the list of problems (NP-complete and harder) presented by M. R. Garey and myself in our book "Computers and Intractability: A Guide to the Theory of NP-Completeness,” W. H. Freeman & Co., San Francisco, 1979.
Book
The Art of Computer Programming
TL;DR: The arrangement of this invention provides a strong vibration free hold-down mechanism while avoiding a large pressure drop to the flow of coolant fluid.
Journal ArticleDOI
Pattern Classification and Scene Analysis.
Book
Pattern classification and scene analysis
Richard O. Duda,Peter E. Hart +1 more
TL;DR: In this article, a unified, comprehensive and up-to-date treatment of both statistical and descriptive methods for pattern recognition is provided, including Bayesian decision theory, supervised and unsupervised learning, nonparametric techniques, discriminant analysis, clustering, preprosessing of pictorial data, spatial filtering, shape description techniques, perspective transformations, projective invariants, linguistic procedures, and artificial intelligence techniques for scene analysis.